Open, source-linked dataset of real-world cyberattacks executed or orchestrated by AI agents. Every field cited, every grade honest. Data layer of Rogue Agent Watch.
dataset cybersecurity stix cti autonomous-agents threat-intelligence ai-agents sandbox-escape ai-security sandbox-evasion mitre-atlas mlsecops prompt-injection llm-security agentic-ai sandbox-eval autonomous-agent-identity rogue-agents autonomous-agent-security rogue-agents-security
-
Updated
Oct 16, 2026 - JavaScript